Channel and feature selection for a surface electromyographic pattern recognition task

Mesa, Iker; Rubio, Ángel; Tubía, Imanol; Nó, J. de; Díaz, Javier

doi:10.1016/j.eswa.2014.03.014

Cited by 46 publications

(15 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Effective feature processing not only reduces the amount of data, but also increases recognition accuracy. In [8,12,16,19], researchers often used timedomain and spectral estimation to extract the features from SEMG signals. This study uses only time-domain methods to extract all features.…”

Section: Feature Extractionmentioning

confidence: 99%

“…It could not only reduce the amount of required computation data efficiently, but also lower effect of reduced identification rates. Additionally, many core methods are proposed for signal identification in previous studies such as backpropagation neural network (BPNN), grey relational analysis (GRA), support vector machine (SVM), and log-linearized Gaussian mixture network (LLGMN) [8,12,[15][16][17]. The time consumption of signal identification in real-time systems is also a concern.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Combining Independent Component and Grey Relational Analysis for the Real-Time System of Hand Motion Identification Using Bend Sensors and Multichannel Surface EMG

Chen

2015

Mathematical Problems in Engineering

View full text Add to dashboard Cite

This paper proposes a portable system for hand motion identification (HMI) using the features from data glove with bend sensors and multichannel surface electromyography (SEMG). SEMG could provide the information of muscle activities indirectly for HMI. However it is difficult to discriminate the finger motion like extension of thumb and little finger just using SEMG; the data glove with five bend sensors is designed to detect finger motions in the proposed system. Independent component analysis (ICA) and grey relational analysis (GRA) are used to data reduction and the core of identification, respectively. Six features are extracted from each SEMG channel, and three features are computed from five bend sensors in the data glove. To test the feasibility of the system, this study quantitatively compares the classification accuracies of twenty hand motions collected from 10 subjects. Compared to the performance with a back-propagation neural network and only using GRA method, the proposed method provides equivalent accuracy (>85%) with three training sets and faster processing time (20 ms). The results also demonstrate that ICA can effectively reduce the size of input features with GRA methods and, in turn, reduce the processing time with the low price of reduced identification rates.

show abstract

Section: Feature Extractionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Combining Independent Component and Grey Relational Analysis for the Real-Time System of Hand Motion Identification Using Bend Sensors and Multichannel Surface EMG

Chen

2015

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…EMG can reflect the motion intention of the human body, and it is widely used in rehabilitation training of lower limb disabled persons [ 8 , 9 , 10 , 11 ]. In order to accurately determine whether the trajectory of EMG-controlled prosthesis is the same as the expected trajectory of the human body, it is very important to determine the acquisition position of the EMG signal of the residual limb [ 12 , 13 , 14 , 15 , 16 , 17 ].…”

Section: Introductionmentioning

confidence: 99%

Selection of EMG Sensors Based on Motion Coordinated Analysis

Liu

Xuan

Zhang

et al. 2021

Sensors

View full text Add to dashboard Cite

The intelligent prosthesis driven by electromyography (EMG) signal provides a solution for the movement of the disabled. The proper position of EMG sensors can improve the prosthesis’s motion recognition ability. To exert the amputee’s action-oriented ability and the prosthesis’ control ability, the EMG spatial distribution and internal connection of the prosthetic wearer is analyzed in three kinds of movement conditions: appropriate angle, excessive angle, and angle too small. Firstly, the correlation characteristics between the EMG channels are analyzed by mutual information to construct a muscle functional network. Secondly, the network’s features of different movement conditions are analyzed by calculating the characteristic of nodes and evaluating the importance of nodes. Finally, the convergent cross-mapping method is applied to construct a directed network, and the critical muscle groups which can reflect the user’s movement intention are determined. Experiment shows that this method can accurately determine the EMG location and simplify the distribution of EMG sensors inside the prosthetic socket. The network characteristics of key muscle groups can distinguish different movements effectively and provide a new strategy for decoding the relationship between limb nerve control and body movement.

show abstract

“…An uncertainty shifted electrode position caused worse classification results. Moreover, few electrodes provide insufficient sEMG features, which decline complex movement classification accuracy [12]. Studies [13] showed that when a person does some movements, the active muscles do not contract simultaneously.…”

Section: Introductionmentioning

confidence: 99%

Upper Arm Motion High-Density sEMG Recognition Optimization Based on Spatial and Time-Frequency Domain Features

Bai

Chen

Yang

2019

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Background. Spatial characteristics of sEMG signals are obtained by high-density matrix sEMG electrodes for further complex upper arm movement classification. Multiple electrode channels of the high-density sEMG acquisition device aggravate the burden of the microprocessor and deteriorate control system’s real-time performance at the same time. A shoulder motion recognition optimization method based on the maximizing mutual information from multiclass CSP selected spatial feature channels and wavelet packet features extraction is proposed in this study. Results. The relationship between the number of channels and recognition rate is obtained by the recognition optimization method. The original 64 electrodes channels are reduced to only 4-5 active signal channels with the accuracy over 92%. Conclusion. The shoulder motion recognition optimization method is combined with the spatial-domain and time-frequency-domain features. In addition, the spatial feature channel selection is independent of feature extraction and classification algorithm. Therefore, it is more convenient to use less channels to achieve the desired classification accuracy.

show abstract

Channel and feature selection for a surface electromyographic pattern recognition task

Cited by 46 publications

References 22 publications

Combining Independent Component and Grey Relational Analysis for the Real-Time System of Hand Motion Identification Using Bend Sensors and Multichannel Surface EMG

Combining Independent Component and Grey Relational Analysis for the Real-Time System of Hand Motion Identification Using Bend Sensors and Multichannel Surface EMG

Selection of EMG Sensors Based on Motion Coordinated Analysis

Upper Arm Motion High-Density sEMG Recognition Optimization Based on Spatial and Time-Frequency Domain Features

Contact Info

Product

Resources

About